Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11733
    Prev
    Next
    INDEX
    Explanations

    activity_ followed by layout names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     également
    -1.20
    に行く
    -1.10
    に行った
    -1.07
     Projektu
    -1.05
    ≳
    -1.04
    に行って
    -1.02
    ᾿
    -1.02
    arest
    -0.98
     trabaja
    -0.96
    心底
    -0.96
    POSITIVE LOGITS
    ?」
    1.13
    🛏
    1.05
    Продам
    1.03
    hörer
    1.03
     inger
    1.02
    灕
    1.00
    Елена
    1.00
    今回は
    1.00
    stdafx
    0.98
    指標
    0.98
    Activations Density 0.001%

    No Known Activations